trace-skill-activitylisted

# Trace skill activity with qvr audit `qvr audit` captures an atomic trace of every tool, file op, and command an agent runs — **attributed to the skill that was active** — into a local SQLite database (`~/.quiver/skillops.db`). It answers "what did this agent actually do, and which skill drove it?" The subsystem is **experimental, opt-in, and disabled by default**; its command surface, storage format, and output shapes may change. ## When to use this - The user wants visibility into agent tool/file/command activity. - They want to attribute actions to the skill that was active. - They want to export traces for external analysis, replay, or archival. This is observability only — it does not change what skills are installed (that's `onboard-skills`) or verify their integrity (that's `verify-skill-supply-chain`). ## How it works (two layers) - **Raw traces** — the agent's own transcript lines and hook payloads, captured verbatim. This is the source of truth (`qvr audit export`, `sessions show`). - **Derived spans** — Turn / Tool / Skill spans projected from the raw traces, as shown by `qvr audit logs`. A deriver must exist for the agent; without one the agent is raw-only and the derived views stay empty (the `DERIVES` column in `status` reports, per agent, whether a deriver exists). ## Workflow ### 1. Enable capture and wire agent hooks `enable` sets `ops.enabled` in config and creates the database. `install-hooks` adds a hook to each detected agent's config th